Multi-Vehicle Perception Data Sharing for Dynamic Object Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles lack timely and accurate identification of dynamic objects in their environment, leading to potential overreactions or underreactions due to limited sensor field-of-view or obstructions, especially in scenarios involving emergency vehicles, road hazards, and weather conditions.
Innovation Solution
Implementing real-time multi-vehicle sensing and perception through a server-orchestrated communication system that enables autonomous vehicles to share and process observation data with each other, supplementing their onboard sensing and perception data to enhance decision-making in uncertain environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous vehicles rely solely on onboard sensors for environment perception, then device complexity is reduced, but measurement precision and reliability of dynamic object identification deteriorate due to limited field-of-view and obstructions
Solution Approach 1:
The patent merges sensing capabilities across multiple autonomous vehicles by having them share sensor data through a communication network. Each vehicle's sensors detect dynamic objects within their respective fields-of-view, and this data is combined to create a comprehensive environmental model that overcomes individual vehicle limitations regarding measurement precision and detection coverage.
Solution Approach 2:
The communication system enables multi-functionality by allowing vehicles to serve both as independent sensing units and as contributors to a collective perception network. The same onboard sensors perform local detection while simultaneously providing data to the broader system, eliminating the need for additional specialized hardware while enhancing measurement precision.
2Reliability
If autonomous vehicles use only their own sensing data for decision-making, then response time is faster, but reliability deteriorates due to potential obstructions and limited perspective
Solution Approach 1:
Vehicles continuously share sensing data with the communication system in real-time, performing preliminary data preparation and coordination before critical decisions are needed. This ongoing data exchange ensures that when a vehicle needs to make a decision about a dynamic object, the relevant information from other vehicles is already available or can be quickly retrieved, maintaining reliability without significant time loss.
Solution Approach 2:
The system implements feedback loops where sensing data from multiple vehicles is continuously exchanged and integrated. This feedback mechanism allows vehicles to update their understanding of the environment in real-time, improving decision-making reliability by confirming or correcting observations from other vehicles while maintaining responsive decision-making through efficient data processing.
3Loss of information
If autonomous vehicles share sensing data in real-time across the fleet, then measurement precision and reliability improve, but device complexity and communication infrastructure requirements worsen
Solution Approach 1:
The patent introduces a communication system as an intermediary that manages data exchange between vehicles. This intermediary layer handles the complexity of real-time data sharing, coordination, and integration, allowing vehicles to achieve complete environmental information without each vehicle needing complex direct communication capabilities with all other vehicles, thus reducing individual device complexity while maintaining information completeness.
Data Source
AI summary
A system includes a first autonomous vehicle (AV) including a sensing system including a set of sensors, a memory storing instructions and a processing device operatively coupled to the memory, wherein the instructions, when executed by the processing device, cause the processing device to perform operations including observing, using data obtained from the sensing system, an event reflecting a scenario within a driving environment, generating a set of event observation data characterizing the event, and causing the set of event observation data to be shared with at least a second AV that is determined to be in a vicinity of the event after the event is observed.


